lsm/PdfPig
1
0
Fork 0
mirror of https://github.com/UglyToad/PdfPig.git synced 2025-10-14 19:05:01 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

strings record encoding used to create them.

Browse Source 
in order to recreate the valid bytes for use in decryption it is necessary to know which encoding was used to read a string token. this is because utf16-be encoding has a byte-order marker which should be included in the resulting bytes.
This commit is contained in:
Eliot Jones
2020-01-26 17:07:58 +00:00
parent 693a3d5958
commit 6cf257a331
5 changed files with 345 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/UglyToad.PdfPig.Tokenization/StringTokenizer.cs
View File

@@ -144,6 +144,7 @@
}
}
StringToken.Encoding encodedWith;
string tokenStr;
if (builder.Length >= 2)
{
@@ -152,24 +153,32 @@
var rawBytes = OtherEncodings.StringAsLatin1Bytes(builder.ToString());
tokenStr = Encoding.BigEndianUnicode.GetString(rawBytes).Substring(1);
encodedWith = StringToken.Encoding.Utf16BE;
}
else if (builder[0] == 0xFF && builder[1] == 0xFE)
{
var rawBytes = OtherEncodings.StringAsLatin1Bytes(builder.ToString());
tokenStr = Encoding.Unicode.GetString(rawBytes).Substring(1);
encodedWith = StringToken.Encoding.Utf16;
}
else
{
tokenStr = builder.ToString();
encodedWith = StringToken.Encoding.Iso88591;
}
}
else
{
tokenStr = builder.ToString();
encodedWith = StringToken.Encoding.Iso88591;
}
token = new StringToken(tokenStr);
token = new StringToken(tokenStr, encodedWith);
return true;
}